mirror of
https://github.com/run-llama/llama-hub.git
synced 2025-08-14 03:31:41 +00:00
e97bb81915
* cr * cr * cr --------- Co-authored-by: Jerry Liu <jerry@robustintelligence.com> Co-authored-by: Jesse Zhang <jessetanzhang@gmail.com>
37 lines
1000 B
Python
37 lines
1000 B
Python
"""Epub Reader.
|
|
|
|
A parser for epub files.
|
|
"""
|
|
|
|
from pathlib import Path
|
|
from typing import Dict, List, Optional
|
|
|
|
from llama_index.readers.base import BaseReader
|
|
from llama_index.readers.schema.base import Document
|
|
|
|
|
|
class EpubReader(BaseReader):
|
|
"""Epub Parser."""
|
|
|
|
def load_data(
|
|
self, file: Path, extra_info: Optional[Dict] = None
|
|
) -> List[Document]:
|
|
"""Parse file."""
|
|
import ebooklib
|
|
import html2text
|
|
from ebooklib import epub
|
|
|
|
text_list = []
|
|
book = epub.read_epub(file, options={"ignore_ncx": True})
|
|
|
|
# Iterate through all chapters.
|
|
for item in book.get_items():
|
|
# Chapters are typically located in epub documents items.
|
|
if item.get_type() == ebooklib.ITEM_DOCUMENT:
|
|
text_list.append(
|
|
html2text.html2text(item.get_content().decode("utf-8"))
|
|
)
|
|
|
|
text = "\n".join(text_list)
|
|
return [Document(text, extra_info=extra_info)]
|